Self-supervised learning has become a popular approach in recent years for its ability to learn meaningful representations without the need for data annotation. This paper proposes a novel image augmentation technique, overlaying images, which has not been widely applied in self-supervised learning. This method is designed to provide better guidance for the model to understand underlying information, resulting in more useful representations. The proposed method is evaluated using contrastive learning, a widely used self-supervised learning method that has shown solid performance in downstream tasks. The results demonstrate the effectiveness of the proposed augmentation technique in improving the performance of self-supervised models.
@article{arxiv.2301.09299,
title = {Self-Supervised Image Representation Learning: Transcending Masking with Paired Image Overlay},
author = {Yinheng Li and Han Ding and Shaofei Wang},
journal= {arXiv preprint arXiv:2301.09299},
year = {2023}
}